Unverified50% confidenceFactExact time
Query2doc achieves LLM-based query expansion by generating short paragraphs, while HyDE does so by generating hypothetical documents.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-query retrieval uses an LLM to automatically generate 3–5 semantically equivalent but differently phrased variant queries for the same question, retrieves results for each separately, and takes the union to improve recall.67% similarUnverifiedThe pipeline consists of four steps: complaint upload, page-by-page parsing by LexSelect, AI semantic extraction, and automatic case creation with write-back to the database.66% similarUnverifiedModular questionnaire design—compressing required questions to the shortest path while retaining optional extension modules—is a common solution for balancing data quality with sample representativeness.65% similarUnverifiedSQL injection can fundamentally isolate data from instructions through parameterized queries, whereas there is currently no equivalent "parameterized" solution for the LLM inference process.65% similarUnverifiedAdvanced RAG introduces Query Rewriting and HyDE (Hypothetical Document Embeddings) before retrieval to optimize query quality, and improves relevance after retrieval through Cross-Encoder re-ranking and context compression.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002093API
curl https://kongchang.com/api/v1/knowledge/claims/1002093MCP
get_claim(id=1002093)